Automatic Motion-Blurred Hand Matting for Human Soft Segmentation in Videos
文献类型:会议论文
作者 | Zhao XM(赵晓梅)1,2; Wu YH(吴毅红)1,2; Wu, Yihong; Zhao, Xiaomei |
出版日期 | 2019 |
会议日期 | 2019-09 |
会议地点 | 台北 |
关键词 | Motion-blurred Hands Matting Synthetic Data Generation Human Soft Segmentation |
卷号 | 2019-September |
DOI | 10.1109/ICIP.2019.8803053 |
页码 | 1450-1454 |
英文摘要 | Accurate hand segmentation is important for human segmentation. However, in videos, hand regions usually have serious motion blur, which reduces segmentation performance obviously. To solve this problem, we propose an automatic matting network to deal with motion-blurred hands. Then we combine the hand alpha mattes provided by matting network and the human segmentation results provided by segmentation network to generate our final human soft segmentation results. In addition, to train the matting network, we need a huge amount of motion-blurred hand images and their groundtruth alpha mattes. However these images are very difficult to obtain. To solve this problem, we propose an efficient semi-automatic synthetic data generation method and generate 36186 synthetic motion-blurred hand images and their alpha mattes. Experiments on synthetic images and real videos show that our method achieves state-of-art matting performance and successfully solve the problem of bad hand segmentation caused by serious motion blur. |
源URL | [http://ir.ia.ac.cn/handle/173211/38541] |
专题 | 自动化研究所_模式识别国家重点实验室_机器人视觉团队 |
通讯作者 | Wu YH(吴毅红); Wu, Yihong |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing 100049, China 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China |
推荐引用方式 GB/T 7714 | Zhao XM,Wu YH,Wu, Yihong,et al. Automatic Motion-Blurred Hand Matting for Human Soft Segmentation in Videos[C]. 见:. 台北. 2019-09. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。